# baseline.muh — Competition vllm launch configuration
# SYNCED FROM computility-run.yaml (the actual deployment config)
#
# This file stores ONLY the vllm server launch config.
# Kernel tuning values live in muh/include/muh/tuning/tuning_*.cuh
# as constexpr structs — NOT here.
#
# Pipeline:
#   muh/tuning/*.cuh (bi100_* values) → gen_patch.py → vllm kernel patches
#   baseline.muh (vllm config)        → gen_yaml.py → computility-run.yaml
#
# CRITICAL: computility-run.yaml is the deployment source of truth.
# This .muh must stay in sync with it.

# --- vllm launch configuration ---
vllm:
  model_path: /model
  served_model_name: llm
  max_model_len: 100000
  gpu_memory_utilization: 0.90
  tensor_parallel: 4
  max_num_seqs: 1
  trust_remote_code: true
  disable_log_requests: true
  disable_frontend_multiprocessing: true
  enable_auto_tool_choice: true
  tool_call_parser: qwen3_coder
  reasoning_parser: qwen3
  enable_prefix_caching: true
  enforce_eager: true
  dtype: half

concurrency: 1

env:
  VLLM_ENGINE_ITERATION_TIMEOUT_S: 3600
  VLLM_ATTENTION_BACKEND: XFORMERS
  ENABLE_CUSTOM_IPC: 1
  PYTHONPATH: /usr/local/corex/lib/python3/dist-packages:/usr/local/corex/lib64/python3/dist-packages
  LD_LIBRARY_PATH: /usr/local/corex/lib64:/usr/local/openmpi/lib
  VLLM_COREX_FA2_LIBRARY: /usr/local/corex/lib64/libcorex_fa2.so
  VLLM_COREX_GDN_LIBRARY: /usr/local/corex/lib64/libcorex_gdn.so
  VLLM_COREX_MOE_LIBRARY: /usr/local/corex/lib64/libcorex_moe.so
  VLLM_REQUEST_METRICS_FILE: /tmp/vllm-request-metrics.jsonl
  VLLM_CACHE_BLOCK_SIZE: 16